{"id":"W4416417137","doi":"10.1007/s11432-025-4676-4","title":"Large multimodal models evaluation: a survey","year":2025,"lang":"en","type":"article","venue":"Science China Information Sciences","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Competence (human resources); Data collection; Evaluation methods; Term (time); Multimodal interaction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01465093,0.0001701098,0.0001541736,0.00107046,0.002304276,0.00166879,0.003921426,0.00005200508,0.00003487457],"category_scores_gemma":[0.001623344,0.0001428057,0.00004045593,0.008383013,0.0008222583,0.01334977,0.0007499743,0.0002017824,0.000186222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001791527,"about_ca_system_score_gemma":0.001927196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001047303,"about_ca_topic_score_gemma":0.00006669278,"domain_scores_codex":[0.9962901,0.0001748063,0.0005063062,0.0005321588,0.001914494,0.0005821139],"domain_scores_gemma":[0.9977722,0.0001837062,0.0002486819,0.0007980067,0.0008617066,0.0001357529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003344643,0.00006947488,0.01253979,0.00001143172,0.000004484602,9.254999e-8,0.004240994,0.1105435,0.0001314872,0.7929707,0.0005414427,0.07894333],"study_design_scores_gemma":[0.0002174985,0.00002020989,0.2673968,0.00001022183,0.00000178218,0.000001531309,0.0000930798,0.7118121,0.0001352921,0.01980233,0.0003900847,0.0001191241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1170049,0.00002959052,0.8119052,0.002361432,0.000556769,0.0005234746,0.00001095503,0.000254271,0.06735343],"genre_scores_gemma":[0.9685228,0.000003608027,0.03051215,0.0008009967,0.00001119081,0.00009056756,0.000009792696,0.000001600348,0.00004722603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.851518,"threshold_uncertainty_score":0.9993676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03383829650789999,"score_gpt":0.3639713949218057,"score_spread":0.3301330984139058,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}